SIENTIAPDE-1645: Expose detailed model training information via a new Prometheus gauge. This gauge, sientia_training_info, records metadata such as dataset sizes, feature count, and evaluation metrics (MSE, MAE, R2) along with the training run's timestamp.

model_manager/activities/training.py

@@ -262,6 +262,18 @@ class Training(SientiaMonitoring):
                     train_result.r2_val
                 )
 
+            mm_metrics.SIENTIA_TRAINING_INFO.labels(
+                pod_id=labels['pod_id'],
+                model_name=train_params.model_name,
+                model_type=train_params.model_type,
+                dataset_train_rows=str(len(train_result.train_data)),
+                dataset_val_rows=str(len(train_result.val_data)),
+                feature_count=str(len(train_params.variable_columns)),
+                mse=str(train_result.mse_val) if train_result.mse_val is not None else '',
+                mae=str(train_result.mae_val) if train_result.mae_val is not None else '',
+                r2=str(train_result.r2_val) if train_result.r2_val is not None else '',
+            ).set(time.time() * 1000)
+
             self.info(f'Starting MLflow run for {train_params.model_type}', metadata)
             with self.mlflow_repository.start_run(
                 model_name=train_params.model_name,

model_manager/metrics.py

@@ -27,6 +27,22 @@ APP_UP = Gauge(
 
 _TRAINING_LABELS = ['pod_id', 'model_name', 'model_type']
 
+SIENTIA_TRAINING_INFO = Gauge(
+    'sientia_training_info',
+    'Metadata and execution timestamp (ms) of the last successful model training run',
+    [
+        'pod_id',
+        'model_name',
+        'model_type',
+        'dataset_train_rows',
+        'dataset_val_rows',
+        'feature_count',
+        'mse',
+        'mae',
+        'r2',
+    ],
+)
+
 SIENTIA_TRAINING_MODEL_TRAINED_TOTAL = Counter(
     'sientia_training_model_trained_total',
     'Number of successfully completed model training runs',